Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations (readOnly/openWorld/idempotent=false) it discloses a lot: x402 exact USDC on Base or Scout credits, three accepted payer mechanisms, a structured payment_required challenge when unpaid, never-fabricated data, refund on refusal, typed 404 for unknown/delisted symbols, and the need to poll /v1/resolutions/:id until horizon_end. It does not cover rate limits or how many calls a debit buys. Note the tension: a tool that debits credits is not obviously side-effect free, though the underlying signal read is non-mutating.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is enormous and dominated by a heavily duplicated instrument list (S01/S05 repeated, X05 five times, X06–X09 six times each), with no reader benefit. The first sentence is cryptic ('x402 exact USDC Base · after paying, poll ...') and pushes the actual purpose past the noise. Most sentences do not earn their place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a paid, multi-step decision tool with an output schema available, it does cover payment rails, refusal/refund semantics, error typing and the post-payment polling loop, which is the hard part. Gaps remain on `question_version` semantics and on how it relates to the sibling ask/get_decision tools, and the qualifier list is so corrupted it is unreliable as an availability reference.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 20%, so the description has to carry the load, and it partially does: it expands `payer` (0x Base address, credit rail, x-tollbridge-payer header, x402 PAYMENT-SIGNATURE), clarifies `asset` accepts any universe symbol, and maps question_id families (S01–S26, X05–X09) to the data each reads. But the mapping is drowned in duplicated, partly garbled entries (X05 listed five times, X06–X09 repeated), and `question_version` is never explained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The leading sentence states a concrete verb+resource: ask a catalog signal through the decision engine for an asset on base, returning probability, confidence, policy verdict, horizons and provenance. It also names which inputs are askable and routes the caller to tollbridge_universe and tollbridge_pricing. It stops short of explicitly distinguishing itself from near-neighbours such as tollbridge_call, tollbridge_calls or tollbridge_get_decision.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It describes an agent loop (get latest → get resolution → ask the NEXT dated sentence) and notes that blocked questions S02/S03/S04 return out_of_scope instead of a gradeless probability, which is genuine when/when-not context. However it never contrasts itself with the obvious alternative ask-tools in the sibling list, leaving the choice to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.